26 citations · 42 across the 9 of their papers we have counts for
16 papers
Multimodal AI Detection for Math-Heavy Scientific Text
Yixuan Huang, Danish Pruthi, Bhuwan Dhingra
As large language models become increasingly capable of generating, and assisting with, scientific writing, there is a need for greater transparency and disclosure around the use o…
Agents Can Use Base Models to Evade AI Detection
Bhuwan Dhingra, Danish Pruthi
We show that coding agents equipped with a base language model can successfully assemble responses from its samples to evade detection. Base models have been shown to evade commerc…
OpenStamp: A Watermark for Open-Source Language Models
Miroojin Bakshi, Saksham Rastogi, Danish Pruthi
With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from…
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Saksham Rastogi, Pratyush Maini, Danish Pruthi
Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary dat…
Goodhart's Law Applies to NLP's Explanation Benchmarks
Jennifer Hsia, Danish Pruthi, Aarti Singh +1
Despite the rising popularity of saliency-based explanations, the research community remains at an impasse, facing doubts concerning their purpose, efficacy, and tendency to contra…
Learning the Legibility of Visual Text Perturbations
Dev Seth, Rickard Stureborg, Danish Pruthi +1
Many adversarial attacks in NLP perturb inputs to produce visually similar strings ('ergo' 'rgo') which are legible to humans but degrade model performance. Althou…